find duplicated files efficiently

#!/bin/bash

v_dir="."
v_output_dir="/tmp/$(basename $0)"
v_sizemin=

# Permet de savoir s'il y a un argument apres le flag
# si pas d'argument, on passe au suivant.
function analyze_arg {
	# si $2 n'est pas vide et ne commence pas par un tiret
	if [ -n "$2" -a "$(echo $2 |cut -c1)" != "-" ]
	then
		eval $1=\"$2\"
		return 2
	else
		return 1
	fi
}

while [ "$#" -gt "0" ] # Tant qu'il y a des arguments
do
	case $1
	in
		-dir) analyze_arg v_dir "$2" ; shift $?  ;;
		-outdir) analyze_arg v_output_dir "$2" ; shift $?  ;;
		-sizemin) analyze_arg v_sizemin "$2" ; shift $?  ;;
		*) echo "Incorrect argument detected"
			echo "$0 [-dir <path(default current)>] [-outdir <path( default /tmp>] [-sizemin <size>]"
			exit 1
			;;
	esac
done

[ -e "$v_output_dir" -a ! -d "$v_output_dir" ] && {
	echo "error: output dir already exists and is not a directory"
	exit 1
}

[ -n "$v_sizemin" ] && v_sizemin="-size +${v_sizemin}M"

[ ! -d "$v_output_dir" ] && mkdir -p "$v_output_dir"

v_files_size="${v_output_dir}/01-files_size.list"
echo "find duplicate files size"
find "${v_dir}" -type f -not -empty ${v_sizemin} -printf "%-25s%p\n" |sort -n |uniq -D -w25 > "${v_files_size}"

v_files_md5="${v_output_dir}/02-files.md5"
echo "md5sum duplicated files size"
cut -b26- "${v_files_size}" |xargs -d"\n" -n1 md5sum |sed "s/  /\x0/" > "${v_files_md5}"

echo "isolate duplicated files found"
v_files_dup="${v_output_dir}/03-files.dup"
uniq -D -w32 "${v_files_md5}" > "${v_files_dup}"

echo "print the result"
v_result="${v_output_dir}/04-result.csv"
awk -F"\0" 'BEGIN {
		l=""
	} {
		if ( l != $1 || l == "" ) {
			printf ("\n%s\0;",$1)
		}
		printf ("\0;%s",$2)
		l = $1
	}
	END {
		printf "\n"
	}' "${v_files_dup}" |sed "/^$/d" |tee "${v_result}"

echo "the result can be found in: '${v_result}'"